Smart Stethoscope - Startup Project from ITMO University Accelerator
The Laeneco team has developed a smart stethoscope that detects a lung disease with more precision than doctors. Further - about the components of the device and its capabilities.
Photo © Laeneco
According to the World Health Organization, respiratory diseases account for 10% of the period of disabled years . And this is one of the most frequent reasons for people applying to clinics (after cardiovascular diseases).
')
The most common method of detecting lung disease is auscultation. He is listening to the sounds caused by the activity of internal organs. Auscultation is known since 1816. The first to put it into practice was a French physician and anatomist Rene Laennec . He is also the inventor of the stethoscope and the author of scientific work describing the main auscultatory phenomena - noise, wheezing, crepitations .
In the XXI century, at the disposal of doctors there are ultrasound devices that allow you not only to hear, but to see the internal organs. Despite this, the method of auscultation is still one of the main medical instruments. For example, the importance of auscultation in medical practice is emphasized by Dr. med. Valentin Fuster. In his study, he cited six cases (they all occurred within 48 hours), when diagnostics with a stethoscope helped to make an accurate diagnosis, which was not obvious in the pictures.
But still the method has its drawbacks. In particular, doctors have no means of objectively monitoring the results of auscultatory research. The sounds that the doctor hears are not recorded anywhere, and the quality of the assessment depends solely on his experience. According to various estimates, the accuracy with which the doctor is able to identify the pathology is approximately 67%.
Engineers from Laeneco , a startup that went through the acceleration program of ITMO University, took up the solution of these problems. They developed a smart stethoscope using machine learning algorithms to detect lung disease from audio recordings.
An electronic stethoscope has a sensitive microphone that picks up a wider frequency range than the human ear. At the same time, doctors have the opportunity to increase the volume of audible noise. This is important when working with full patients, as the sound penetrates worse through thick human tissue. Plus, the function is relevant for health workers in the age, in which the acuity of hearing is not the same as in youth.
Deep neural networks help to identify sounds that indicate the presence of the disease. Now the accuracy of their work is 83%, but in theory this indicator can be increased to 98%. The startup team is already collecting new data to expand the training set.
Photo: Pixino / PD
The smart stethoscope is paired with a smartphone. The application gives users recommendations regarding the conduct of diagnostics, stores and processes records, displays measurement results. Thanks to this device can be used by people who do not have medical education.
The Laeneco team is convinced that a smart stethoscope will help reduce the likelihood of chronic lung diseases, and plans to expand the capabilities of the tool. One of the main tasks is to develop functionality for detecting heart pathologies.
The Laeneco team consists of three people: Evgeny Putin, Sergey Chukhontsev and Ilya Skorobogatov.
Evgeny works as a software engineer at the Computer Technologies Laboratory of the ITMO University and leads the Kaggle Club circle on solving practical problems of machine learning. He is also the author of Aging.ai , a resource that can predict a patient’s age by blood analysis.
The second member of the team, Sergey, graduated from the Institute of Law at the Udmurt State University and is one of the authors of the concept of a networked plant. It is designed to manage multiple independent productions.
As for Ilya, he is a graduate of ITMO University with a degree in Information Technology and Programming, who has long been involved in the automation of production and workflow. The idea to create a smart stethoscope came precisely to him when he was developing a sensor for analyzing sounds emitted by machine tools.
In 2017, a team of Laeneco completed the Future Technologies ITMO acceleration program. Participants formed a business model and developed an MVP smart stethoscope. The system was presented at the startup festival * SHIP-2017 in Finland and St. Petersburg Forum SPIEF'18. Also in 2018, the project became the winner of the pitch-session “ Japan - the country of ascending start-ups ”, organized by the Technopark of the ITMO University together with experts from Asia. At the same time, Laeneco received an offer to bring their product to the Japanese market.
PS If you are related to ITMO University and would like to tell about your project or scientific work in our blog on Habré, send potential itmo topics to BOS .
Photo © Laeneco
Difficulties associated with the treatment of lung diseases
According to the World Health Organization, respiratory diseases account for 10% of the period of disabled years . And this is one of the most frequent reasons for people applying to clinics (after cardiovascular diseases).
')
The most common method of detecting lung disease is auscultation. He is listening to the sounds caused by the activity of internal organs. Auscultation is known since 1816. The first to put it into practice was a French physician and anatomist Rene Laennec . He is also the inventor of the stethoscope and the author of scientific work describing the main auscultatory phenomena - noise, wheezing, crepitations .
In the XXI century, at the disposal of doctors there are ultrasound devices that allow you not only to hear, but to see the internal organs. Despite this, the method of auscultation is still one of the main medical instruments. For example, the importance of auscultation in medical practice is emphasized by Dr. med. Valentin Fuster. In his study, he cited six cases (they all occurred within 48 hours), when diagnostics with a stethoscope helped to make an accurate diagnosis, which was not obvious in the pictures.
But still the method has its drawbacks. In particular, doctors have no means of objectively monitoring the results of auscultatory research. The sounds that the doctor hears are not recorded anywhere, and the quality of the assessment depends solely on his experience. According to various estimates, the accuracy with which the doctor is able to identify the pathology is approximately 67%.
Engineers from Laeneco , a startup that went through the acceleration program of ITMO University, took up the solution of these problems. They developed a smart stethoscope using machine learning algorithms to detect lung disease from audio recordings.
Opportunities and prospects for solutions
An electronic stethoscope has a sensitive microphone that picks up a wider frequency range than the human ear. At the same time, doctors have the opportunity to increase the volume of audible noise. This is important when working with full patients, as the sound penetrates worse through thick human tissue. Plus, the function is relevant for health workers in the age, in which the acuity of hearing is not the same as in youth.
Deep neural networks help to identify sounds that indicate the presence of the disease. Now the accuracy of their work is 83%, but in theory this indicator can be increased to 98%. The startup team is already collecting new data to expand the training set.
Photo: Pixino / PD
The smart stethoscope is paired with a smartphone. The application gives users recommendations regarding the conduct of diagnostics, stores and processes records, displays measurement results. Thanks to this device can be used by people who do not have medical education.
The Laeneco team is convinced that a smart stethoscope will help reduce the likelihood of chronic lung diseases, and plans to expand the capabilities of the tool. One of the main tasks is to develop functionality for detecting heart pathologies.
O laeneco
The Laeneco team consists of three people: Evgeny Putin, Sergey Chukhontsev and Ilya Skorobogatov.
Evgeny works as a software engineer at the Computer Technologies Laboratory of the ITMO University and leads the Kaggle Club circle on solving practical problems of machine learning. He is also the author of Aging.ai , a resource that can predict a patient’s age by blood analysis.
The second member of the team, Sergey, graduated from the Institute of Law at the Udmurt State University and is one of the authors of the concept of a networked plant. It is designed to manage multiple independent productions.
As for Ilya, he is a graduate of ITMO University with a degree in Information Technology and Programming, who has long been involved in the automation of production and workflow. The idea to create a smart stethoscope came precisely to him when he was developing a sensor for analyzing sounds emitted by machine tools.
In 2017, a team of Laeneco completed the Future Technologies ITMO acceleration program. Participants formed a business model and developed an MVP smart stethoscope. The system was presented at the startup festival * SHIP-2017 in Finland and St. Petersburg Forum SPIEF'18. Also in 2018, the project became the winner of the pitch-session “ Japan - the country of ascending start-ups ”, organized by the Technopark of the ITMO University together with experts from Asia. At the same time, Laeneco received an offer to bring their product to the Japanese market.
Other habraposts of ITMO University:
- ITMO University Research Digest: trends and new achievements of scientists
- Mechanized arms and manipulators - about our robotics laboratory
- How ITMO University works: a tour of the cyber-physical systems lab
- FabLab University ITMO: DIY-co-working for creative people
PS If you are related to ITMO University and would like to tell about your project or scientific work in our blog on Habré, send potential itmo topics to BOS .
Source: https://habr.com/ru/post/445028/
All Articles